skill-from-github
Create skills by learning from high-quality GitHub projects
1.53k repo starsObserved in 3 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
skill-from-masters
通过真实案例创建高质量skill。先找黄金案例和失败案例，归纳什么有效什么无效，再用理论解释为什么。skill是干活的，要从实践中学习，不是从书本中学习。触发词："帮我创建一个skill"、"我想做一个skill来..."
1.53k repo starsObserved in 2 repos
Agent Building
agent-knowledge
Your long-term knowledge pages. Read them at session start. Create new pages when you learn something worth remembering across sessions. Pages auto-update from your conversations via Hindsight.
1.53k repo starsObserved in 1 repos
Agent Building
validate-evaluator
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
1.52k repo starsObserved in 1 repos
Agent Building
backtesting-configuration
Configures TimeSeriesFold parameters for backtesting based on deployment scenarios. Maps business requirements (retraining frequency, forecast horizon, data budget) to cross-validation strategy parameters. Use when the user describes how they plan to deploy or evaluate a model.
1.51k repo starsObserved in 2 repos
Agent Building
agent-collaboration
Proma 协作子 Agent Skill。当需要并行探索多个方向（多样性探索）、对抗性审查验证已有方案、或多个长耗时独立任务需要真实可见的子会话时触发。用于判断是否以及如何调用 Proma 内置 collaboration 工具创建协作子会话。简单搜索、短调研、单文件修改、一次性代码审查由父会话直接使用普通工具完成。
1.51k repo starsObserved in 1 repos
Agent Building
tool-builder
交互式创建和管理 Chat 模式的自定义 HTTP 工具。当用户想要创建新的 API 工具、配置 Chat 工具、添加自定义工具、管理自定义工具、或说"帮我创建一个 XX 工具"时使用此 Skill。也适用于调试、修复或删除已有的自定义工具。
1.51k repo starsObserved in 1 repos
Agent Building
task-creator
SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the user wants to create a new SkillsBench task, scaffold a task from an existing workflow (notebook, Excel workbook, document, dataset), convert a prompt or a benchmark item into a SkillsBench task, write skills for a task, or prepare a SkillsBench PR. Pairs with `task-review` (run that as a self-check before submitting).
1.51k repo starsObserved in 1 repos
Agent Building
om-create-agents-md
Create or rewrite AGENTS.md files for Open Mercato packages and modules. Use this skill when adding a new package, creating a new module, or when an existing AGENTS.md needs to be created or refactored. Ensures prescriptive tone, the Always/Ask First/Never/Validation Commands boundary structure, MUST-style rules, checklists, and consistent structure across all agent guidelines.
1.50k repo starsObserved in 1 repos
Agent Building
om-create-ai-agent
Build, override, or extend a typed Open Mercato AI agent (chat or structured-object) using the unified AI framework — declare `ai-agents.ts`, register tool packs via `defineAiTool`, patch existing agents with `aiAgentExtensions`, configure agentic loop controls (`loop.stopWhen` / `loop.prepareStep` / `loop.budget` / `executionEngine`), gate mutations through the approval contract, wire ACL features, and embed `<AiChat>` into a backoffice or portal page. Works in both the monorepo (`packages/<x>/src/modules/<module>/`) and standalone projects (`apps/<app>/src/modules/<module>/` or `node_modules/@open-mercato/<package>` consumers). Triggers on "create AI agent", "add AI agent", "build AI assistant", "extend AI agent", "override AI agent", "add tool to existing agent", "wire ai-agents.ts", "add ai-tools.ts", "embed AiChat", "agent for module", "agentic loop", "configure loop budget", "tool-loop-agent".
1.50k repo starsObserved in 1 repos
Agent Building